File size: 8,157 Bytes
81cd825 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 |
05/10/2024 16:54:21 - INFO - transformers.tokenization_utils_base - loading file vocab.json from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/vocab.json 05/10/2024 16:54:21 - INFO - transformers.tokenization_utils_base - loading file merges.txt from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/merges.txt 05/10/2024 16:54:21 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/tokenizer.json 05/10/2024 16:54:21 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at None 05/10/2024 16:54:21 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at None 05/10/2024 16:54:21 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/tokenizer_config.json 05/10/2024 16:54:21 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 05/10/2024 16:54:21 - INFO - llmtuner.data.loader - Loading dataset joshcarp/evy-dataset... 05/10/2024 16:54:23 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/config.json 05/10/2024 16:54:23 - INFO - transformers.configuration_utils - Model config Qwen2Config { "_name_or_path": "Qwen/Qwen1.5-0.5B", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 2816, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 } 05/10/2024 16:55:38 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/model.safetensors 05/10/2024 16:55:38 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float32. 05/10/2024 16:55:38 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151643, "use_cache": false } 05/10/2024 16:55:40 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM. 05/10/2024 16:55:40 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen1.5-0.5B. If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training. 05/10/2024 16:55:40 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/generation_config.json 05/10/2024 16:55:40 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151643, "max_new_tokens": 2048 } 05/10/2024 16:55:40 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled. 05/10/2024 16:55:40 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference. 05/10/2024 16:55:40 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA 05/10/2024 16:55:40 - INFO - llmtuner.model.loader - trainable params: 786432 || all params: 464774144 || trainable%: 0.1692 05/10/2024 16:55:40 - INFO - transformers.trainer - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching. 05/10/2024 16:55:41 - INFO - transformers.trainer - ***** Running training ***** 05/10/2024 16:55:41 - INFO - transformers.trainer - Num examples = 235 05/10/2024 16:55:41 - INFO - transformers.trainer - Num Epochs = 3 05/10/2024 16:55:41 - INFO - transformers.trainer - Instantaneous batch size per device = 2 05/10/2024 16:55:41 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 16 05/10/2024 16:55:41 - INFO - transformers.trainer - Gradient Accumulation steps = 8 05/10/2024 16:55:41 - INFO - transformers.trainer - Total optimization steps = 42 05/10/2024 16:55:41 - INFO - transformers.trainer - Number of trainable parameters = 786,432 05/10/2024 16:56:35 - INFO - llmtuner.extras.callbacks - {'loss': 3.1521, 'learning_rate': 4.8272e-05, 'epoch': 0.34} 05/10/2024 16:58:24 - INFO - llmtuner.extras.callbacks - {'loss': 2.7178, 'learning_rate': 4.3326e-05, 'epoch': 0.68} 05/10/2024 17:00:15 - INFO - llmtuner.extras.callbacks - {'loss': 2.7124, 'learning_rate': 3.5847e-05, 'epoch': 1.02} 05/10/2024 17:01:32 - INFO - llmtuner.extras.callbacks - {'loss': 3.0056, 'learning_rate': 2.6868e-05, 'epoch': 1.36} 05/10/2024 17:03:03 - INFO - llmtuner.extras.callbacks - {'loss': 2.6855, 'learning_rate': 1.7631e-05, 'epoch': 1.69} 05/10/2024 17:06:33 - INFO - llmtuner.extras.callbacks - {'loss': 2.3657, 'learning_rate': 9.4128e-06, 'epoch': 2.03} 05/10/2024 17:08:15 - INFO - llmtuner.extras.callbacks - {'loss': 2.5569, 'learning_rate': 3.3494e-06, 'epoch': 2.37} 05/10/2024 17:10:03 - INFO - llmtuner.extras.callbacks - {'loss': 2.9284, 'learning_rate': 2.7923e-07, 'epoch': 2.71} 05/10/2024 17:10:42 - INFO - transformers.trainer - Training completed. Do not forget to share your model on huggingface.co/models =) 05/10/2024 17:10:42 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen1.5-0.5B/lora/train_2024-05-10-16-53-38 05/10/2024 17:10:42 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /Users/joshcarp/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B/snapshots/8f445e3628f3500ee69f24e1303c9f10f5342a39/config.json 05/10/2024 17:10:42 - INFO - transformers.configuration_utils - Model config Qwen2Config { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 2816, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 } 05/10/2024 17:10:42 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen1.5-0.5B/lora/train_2024-05-10-16-53-38/tokenizer_config.json 05/10/2024 17:10:42 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen1.5-0.5B/lora/train_2024-05-10-16-53-38/special_tokens_map.json 05/10/2024 17:10:42 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields: {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} |